AI Innovation Institute

Please join us this Friday, February 13th for the CSE 600 seminar given by Associate Professor Debswapna Bhattacharya, from the Department of Computer Science at Virginia Tech.

Abstract: Building a model of a biological system that can provide actionable hypotheses to form a solid foundation for experimental and theoretical analyses is one of the key challenges in biology and medicine. In this talk, I will present my group's ongoing work in developing, evaluating, and disseminating a new generation of computational methods for biomolecular modeling powered by artificial intelligence (AI) and machine learning (ML). First, I will introduce a new generation of AI/ML methods for improved modeling and characterization of protein-nucleic acid assemblies by deep graph learning using embeddings from biological large language models (LLMs) as well as geometric attention-enabled pairing of heterogeneous biological LLMs, a previously unexplored avenue. Then, I will present a novel generative deep learning model based on equivariant flow matching for end-to-end generation of all-atom RNA 3D structural ensemble. Finally, I will outline my future research directions on attaining atomic-level accuracy in computational modeling of biomolecules and their assemblies at scale.

Speaker: Debswapna Bhattacharya is an Associate Professor in the Department of Computer Science at Virginia Tech. He received his Ph.D. in Computer Science from the University of Missouri-Columbia in 2016. Before joining Virginia Tech in 2022, he was an Assistant Professor at Auburn University from 2017 to 2021. His research interests lie at the intersection of computational biology and machine learning, with a particular focus on artificial intelligence for computational structural biology, specifically in modeling and characterization of biomolecular structures and interactions. His research group has been developing novel computational and data-driven methods, software, and information systems for diverse biomolecular modeling problems, ranking among the best methods in community-wide blind assessments and serving the worldwide community of biomedical users. He received various research awards (NSF CAREER Award, NIH Maximizing Investigators' Research Award, NSF National AI Research Resource Award) and numerous institutional honors (National Distinction and Outstanding Contributor at Virginia Tech, Ginn Faculty Fellowship at Auburn University, Outstanding Engineering Faculty Award at Auburn University).
Location: NCS 120

Join us at the Center for Excellence in Learning and Teaching (CELT) for an interactive Zoom workshop on Generative AI designed for faculty and staff interested in enhancing teaching and assessment practices, increasing student engagement, and navigating the rapidly evolving landscape of AI tools. Participants will be introduced to common AI tools, explore potential instructional uses, and discuss key considerations such as academic integrity, transparency, and equity.

Register now: https://stonybrook.zoom.us/meeting/register/6js1eP64T1ys8tyU57EJ7Q#/registration

The Forty-Second International Conference on Machine Learning will take place at the Vancouver Convention Center from July 13th to July 19th. Register here.

Dates: Friday, April 2, 2021 - 4:00pm to 5:00pm Location: Zoom - contact events@cs.stonybrook.edu for Zoom info.

Abstract: This talk is about the two ends of LLM training: pre-training and in-deployment learning. I will present an approach to disentangle knowledge from skill in model pre-training. This brings about a new class of LLMs that externalize knowledge, with dramatically different characteristics from common LLMs along dimensions of scale, factuality, and updateability. On the other end, I will discuss two in-deployment learning methods. I will describe how in-context learning abilities extend beyond supervised settings, showing that LLMs display in-context reinforcement learning from rewards. Finally, if time allows, I will describe continual learning from implicit interaction signals, demonstrating that LLMs can retrospectively decode latent interaction cues by observing how humans respond to their outputs.

Bio: Yoav Artzi is an Associate Professor in the Department of Computer Science and Cornell Tech at Cornell University, a visiting faculty researcher at Google DeepMind, and arXiv's associate faculty director. His research focuses on language modeling and learning in interactive and situated scenarios. His work was acknowledged by awards and honorable mentions at ACL, EMNLP, NAACL, and IROS, as well as a TACL test-of-time award. Yoav holds a B.Sc. from Tel Aviv University and a Ph.D. from the University of Washington.

Location: NCS 120

2020 Annual Conference of the Association for Computational Linguistics Online format - https://acl2020.org/

Abstract: Pre-trained diffusion and flow matching models have made visual generation remarkably powerful, enabling high-fidelity synthesis of images and videos from natural language prompts. However, their behavior is still largely dictated by the pre-training data distribution and likelihood objective, which do not directly encode downstream desiderata such as fine-grained semantic alignment, controllability, or realism. This gap motivates post-training: starting from a base generator and further optimizing it with additional supervision signals derived from human or reward model preferences.This work presents post-training for visual generative models through two complementary case studies. First, Hummingbird addresses the problem of fine-grained contextual alignment in image-text-to-image generation. We introduce a multimodal context evaluator that scores the consistency between rich contextual descriptions and generated images, capturing fine-grained alignment beyond global CLIP similarity. By directly backpropagating these differentiable rewards through the diffusion sampler, Hummingbird substantially improves semantic faithfulness while preserving high visual quality.
Second, PISCES tackles post-training for text-to-video generation, where alignment is inherently semantic-spatio-temporal. We show that naive VLM-based rewards suffer from distributional mismatch and token-level misalignment, leading to reward hacking and suboptimal optimization. PISCES introduces a bi-objective, Optimal Transport (OT)-aligned reward module: distributional OT using Neural Optimal Transport to align text and video embedding distributions, and discrete, partial OT over a spatio-temporal cost matrix to capture semantic alignment at the token level. These rewards are integrated into both direct backpropagation and GRPO-style optimization to post-train state-of-the-art text-to-video generators. Together, Hummingbird and PISCES provide a unified view of how carefully designed visual reward models, coupled with OT-based representation alignment, can reliably improve the downstream behavior of pre-trained image and video generators.

Speaker: Minh Quan Le

Location: NCS 220

Zoom: https://stonybrook.zoom.us/j/94798224254?pwd=CFraer25qnpORbJ14aAVHRwaSJOjJM.1

Abstract: Artificial intelligence (AI) is rapidly transforming scientific discovery, enabling breakthroughs in areas ranging from drug discovery to modeling complex physical systems. In the life sciences, AI has traditionally been applied to prediction tasks such as classifying molecules as toxic or non-toxic, estimating drug properties, or solving partial differential equations. These discriminative models have proven powerful, but they are inherently limited to mapping existing inputs to deterministic outputs. A new wave of methods is shifting the paradigm from discrimination to generation: creating new possibilities, such as generating novel molecules or designing new drugs. By reframing AI as both a predictive and generative engine, this shift offers new pathways for accelerating discovery and innovation in life sciences at an unprecedented scale. This talk will cover several aspects of AI for Science (AI4Sci), beginning with advances in discriminative models for molecular systems and solving PDEs, and then turning to generative approaches, including diffusion models for 3D molecular generation and large language models for drug editing. Together, these developments illustrate how moving from prediction to creation is redefining what AI can contribute to science.

Bio: Wenhan Gao is a fourth-year Ph.D. student in Applied Mathematics under the supervision of Professor Yi Liu. He was also a Staff Research Scientist Intern at VISA Research, where he worked on large language models (LLMs) and multi-agent systems for commerce. Wenhan's research focuses on AI for Science (AI4Sci), with a particular emphasis on generative AI. His work looks deep into the fundamental mechanisms of AI models when applied to scientific tasks, and he strives to incorporate established scientific priors, such as symmetry, into model design. He has published papers as a first or corresponding author in leading AI and computational venues, including ICLR, ICML, NeurIPS, TMLR, ACL, and the Journal of Computational Physics. In addition to his research, Wenhan has served as a reviewer and oral session chair for top AI conferences and as a lecturer for both undergraduate and graduate courses at Stony Brook University.

Location: IACS Seminar Room or Zoom

This seminar will take place in person and online*

Join Zoom Meeting: https://stonybrook.zoom.us/j/91670093552?pwd=2EcniXqPZLTpa4ZBKRs1zAjYqs1LS0.1

Meeting ID: 916 7009 3552
Passcode: 434045